Trent

Find related sources

find_related_sources

Read-only

Find artifacts on connected platforms that relate to a repository.

Show the results to the customer and let them correct the selection before
attaching anything. Search again by name, narrow to one connector, or drop
unwanted items. This tool reads the platforms. Pass the chosen items to
create_project or update_project as sources to attach them in one call.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "find_related_sources"
  }
}

Input Schema

Name	Required	Description
`repo`	No	A repository as owner/name, for use before creating a project.
`query`	No	Search by name, e.g. the title of a Notion page. Given, widens past exact matches.
`container`	No	A platform container to browse within.
`project_id`	No	Rank artifacts by this project's repositories. Give this, repo, or query.
`connector_id`	No	Connector to search. Defaults to every connected connector.
`suggestions_only`	No	Restrict results to artifacts with an exact repository match. A query or container takes precedence over this setting.

Output Schema

Name	Required	Description
`error`	No	True when the call itself failed. False for successful calls, including a scan still running, an already approved plan, or a repository classified as non-agentic. The reason field describes these workflow states.
`items`	No	Artifacts on connected platforms that relate to the project or repository. suggested is true for an exact repository match; matched_repo identifies the repository. Pass the items the customer chooses to create_project or update_project as sources.
`reason`	No	A stable snake_case code from the allowed set. Present on every error and on successful calls that carry a workflow state.
`scopes`	No	Containers that match (a Linear team or project, a Notion database or page): pass one as source_scopes to attach everything in it. Returned for a query or inside a container.
`message`	No	Exactly one sentence written for the user. Never raw exception text or a backend error string, which may expose private details.
`metadata`	No	Caller metadata, such as 'expiration_warning'. Substantive results have their own fields. Never includes exception or backend error text, which may expose private details.
`truncated`	No	True when more artifacts matched than were returned; narrow the query.
`next_steps`	No	Recommended next actions, in order.
`not_connected`	No	Requested connectors awaiting connection in this workspace.
`connections_url`	No	The app's connections page, when a person needs to act there.
`suggestions_only`	No	True when every returned artifact is an exact repository match. Pass a query to widen the search.
`connection_problems`	No	Connections whose search failed, each with the platform's or server's reason. A person can fix them in the app at connections_url.
`connectors_searched`	No	Connectors that were searched.
`retry_after_seconds`	No	With reason rate_limited, how many seconds Trent asks the caller to wait.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 30, 2026

addedOutput schema / properties / retry_after_seconds

Added value: +{
+  "anyOf": [
+    {
+      "type": "integer"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "With reason rate_limited, how many seconds Trent asks the caller to wait.",
+  "title": "Retry After Seconds"
+}

First observedOct 23, 2026

TDQS

A4.2/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The annotations already declare readOnlyHint=true and openWorldHint=true, and the description adds useful behavior beyond that: it states that the tool reads the platforms and does not attach anything itself. It also explains the downstream handoff to create_project or update_project for attaching sources in one call.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with the core purpose and then covers review, refinement, read-only behavior, and the downstream attach step in four tight sentences. Every sentence contributes useful guidance without repetition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an open-world, read-only search tool with six optional parameters and an output schema, the description covers the key workflow: search, show results, refine, and pass selected items to create/update. Details about parameter interactions remain delegated to the fully documented schema, which is appropriate, though the description could explicitly acknowledge the optional-parameter combinations.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so all six parameters, defaults, and precedence notes are already documented in the schema. The description adds workflow-level meaning for refining by name and narrowing by connector, but it does not materially deepen parameter semantics beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: find artifacts on connected platforms that relate to a repository. It clearly positions the tool as a read/search step before attaching sources rather than a mutation, so an agent can distinguish it from create_project and update_project.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives clear workflow guidance: show results to the customer, let them correct the selection, refine with name/connector filters, and then pass chosen items to create_project or update_project. It does not explicitly say when not to use it versus list_connected_sources or get_artifact, so it falls short of full alternative guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Trent tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.